phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

[inference api] modify content types so they follow a more standard structure (#841)

Browse source 
Some small updates to the inference types to make them more standard

Specifically:
- image data is now located in a "image" subkey
- similarly tool call data is located in a "tool_call" subkey

The pattern followed is `dict(type="foo", foo=<...>)`
This commit is contained in:
Ashwin Bharambe 2025-01-22 12:16:18 -08:00 • committed by GitHub
parent caa8387dd2
commit 07b87365ab
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 104 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
View file

@ -423,7 +423,7 @@ class ChatAgent(ShieldRunnerMixin):
step_id=step_id,
delta=ToolCallDelta(
parse_status=ToolCallParseStatus.succeeded,
content=ToolCall(
tool_call=ToolCall(
call_id="",
tool_name=MEMORY_QUERY_TOOL,
arguments={},
@ -525,7 +525,7 @@ class ChatAgent(ShieldRunnerMixin):
delta = event.delta
if delta.type == "tool_call":
if delta.parse_status == ToolCallParseStatus.succeeded:
tool_calls.append(delta.content)
tool_calls.append(delta.tool_call)
if stream:
yield AgentTurnResponseStreamChunk(
event=AgentTurnResponseEvent(
@ -639,7 +639,7 @@ class ChatAgent(ShieldRunnerMixin):
tool_call=tool_call,
delta=ToolCallDelta(
parse_status=ToolCallParseStatus.in_progress,
content=tool_call,
tool_call=tool_call,
),
)
)